Skip to main content
skill CX Codex

portfolio-review — Claude Code skill: portfolio analysis and install

The portfolio-review Claude Code skill reviews Indian stock portfolios for concentration, risk and rebalancing options. It runs on requests to assess a portfolio or after a broker holdings file is uploaded.

MIT ★ 69 updated 2026-11-13

Install into Claude Code · Plugin marketplace All methods and platforms ↓
/plugin marketplace add Shubhamkumartrichy/claude-trading-skills-india
/plugin install india-trading-skills@india-trading-skills
Open on GitHub

What portfolio-review does

The skill calculates portfolio value, unrealised P&L, stock and sector weights, concentration and risk. It flags pledged shares, SME stocks and surveillance status, then measures beta against NIFTY and identifies correlated groups. Results use INFO, WARN and REVIEW labels; the skill does not tell users to sell.

It accepts CSV files with symbol, qty, buy_price and ltp, as well as exports from Zerodha Console, Kite and Groww. Add buy_date to calculate holding periods for individual lots. The rebalancing plan accounts for taxes and charges. Keep broker files local and out of the repository.

The commands run scripts/portfolio.py: review checks holdings, risk measures portfolio risk, and rebalance prepares a trade plan. For risk, daily price files can be supplied through --prices-dir along with the NIFTY benchmark. Lot-level holding-period calculations need buy_date.

What it helps with

  • calculate stock and sector weights in a portfolio
  • spot concentration across companies or business groups
  • measure beta and exposure to stop-loss levels
  • prepare a tax- and charge-aware rebalance plan
  • identify lots nearing long-term tax treatment

Example prompts for the agent

  • Review holdings.csv and show the sector weights.
  • Measure portfolio risk against NIFTY using the data in prices/.
  • Prepare a rebalance plan for holdings.csv without selling.

How to install portfolio-review

1Plugin marketplace

/plugin marketplace add Shubhamkumartrichy/claude-trading-skills-india
/plugin install india-trading-skills@india-trading-skills

This installs the whole india-trading-skills plugin with all its skills

2Skills CLI (Vercel)

npx skills add Shubhamkumartrichy/claude-trading-skills-india --skill portfolio-review -a claude-code

3Manually: put the files in place

~/.claude/skills/portfolio-review/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/portfolio-review/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about portfolio-review

How do I install portfolio-review in Claude Code?

Add the marketplace with /plugin marketplace add Shubhamkumartrichy/claude-trading-skills-india, then install the plugin with /plugin install india-trading-skills@india-trading-skills.

What does portfolio-review do?

It analyses Indian stock holdings, reports allocation and risk, flags concentration, and prepares a rebalancing plan that accounts for tax and charges.

What data does portfolio-review need?

The holdings file needs symbol, qty, buy_price and ltp. Include buy_date to calculate holding periods for individual lots.

Source text

SKILL.md · MIT
---
name: portfolio-review
description: |
  Health check for an Indian delivery (CNC) stock portfolio from a holdings CSV or a Zerodha Console,
  Kite, Groww or broker-MCP export: value and unrealised P&L, position and sector weights, top-5/top-10
  concentration, business-group exposure (Adani, Tata...), large/mid/small mix against a target,
  pledged, SME and surveillance flags, a per-lot STCG→LTCG countdown, volatility, beta vs NIFTY,
  drawdown, correlated clusters, portfolio heat to stops, and a tax-aware rebalance plan with charges.

  Use when the user asks: "review my portfolio", "am I too concentrated", "sector allocation of my
  holdings", "how risky is my portfolio / what is my beta", "how much am I risking to my stops",
  "rebalance to equal weight", "what should I trim", "which holdings turn long-term soon", or
  uploads a holdings file from their broker.
---

# Portfolio Review (India)

Look at the whole book before the next trade. This skill reports facts and flags (INFO / WARN /
REVIEW). It never says "sell": every flag is a prompt for the user to re-check a thesis.

## Commands

```bash
python3 scripts/portfolio.py review holdings.csv --cash 200000                    # weights, flags, tax clock
python3 scripts/portfolio.py review console.xlsx --sheet Equity --max-stock 8 --mcap-target 50/30/20
python3 scripts/portfolio.py risk holdings.csv --prices-dir prices/ --benchmark NIFTY    # or --yf
python3 scripts/portfolio.py rebalance holdings.csv --cash 50000                   # equal weight
python3 scripts/portfolio.py rebalance holdings.csv --targets targets.csv --broker groww --realized-ltcg 40000
python3 scripts/portfolio.py rebalance holdings.csv --cash 75000 --no-sell         # deploy new money only
```

Every command takes `--as-of YYYY-MM-DD` and `--json`. `--prices-dir` holds daily candles named
`SYMBOL.csv` or `SYMBOL.json` (any format `../technical-analysis/scripts/ta.py` reads) plus `NIFTY.csv`.
Targets file: `symbol,weight[,price]` or `sector,weight`, in percent. Weight 0 means exit; symbols
or sectors left out stay unchanged. A price column lets you add a stock you do not hold yet.

## Input columns

Required: `symbol`, `qty`, `buy_price` (average cost), `ltp`. Strongly recommended: `buy_date`, with one
row per lot, as in `../indian-tax-for-traders/scripts/tax.py` harvest files. Optional: `sector`,
`mcap` (large/mid/small, or a number in ₹ crore), `group`, `stop`, `pledged_qty`, `series` (EQ/BE/SM...),
`sme`, `illiquid`, `surveillance` (ASM/GSM text), `promoter_pledge` (%), `isin`, `exchange`, `fmv_2018`.

Broker headers are mapped automatically, and preamble rows above the header are skipped:

| Source | Headers recognised | Status |
|---|---|---|
| Kite Connect / Kite MCP `get_holdings` | `tradingsymbol`, `quantity` + `t1_quantity`, `average_price`, `last_price`, `collateral_quantity`, `isin`, `exchange` | Checked against the Kite Connect v3 docs |
| Zerodha Console holdings (XLSX) | Symbol, ISIN, Sector, Quantity Available, Quantity Long Term, Quantity Pledged (Margin/Loan), Average Price, Previous Closing Price | Assumed. Compare with your file |
| Kite web holdings CSV | Instrument, Qty., Avg. cost, LTP, Cur. val | Assumed |
| Groww holdings statement (Reports) | Stock Name, ISIN, Quantity, Average buy price, Buy value, Closing price/value | Assumed. Gives company names, so add a `symbol` column before running `risk --yf` |

Broker MCPs (`broker-integration`): call the holdings tool and write a CSV with one row per holding
using the fields above. Keep the raw field names; the mapper understands them. Broker exports carry
**no buy dates**. Console's "Quantity Long Term" is still used, but for a lot-level countdown, rebuild
open lots with `tax.py tradebook` and add `buy_date`. Keep holdings files local. Do not commit them.

## Defaults and why

| Setting | Default | Reason |
|---|---|---|
| `--max-stock` | 10% of capital | One bad result or fraud should not sink the book. REVIEW above 2× |
| `--max-sector` | 25% | Sectors move together on policy, commodity and rate news |
| `--max-group` | 20% | Group companies share promoters, lenders and governance risk |
| `--mcap-target` | 60/25/15 | A core-heavy mix for a retail investor. Change it to match your plan |
| `--mcap-cutoffs` | ₹1,00,000 cr / ₹33,000 cr | Rough stand-ins for AMFI's rank-based list (top 100 / 101–250). Update every half-year |
| `--loser-pct` | 20% below cost | A decline that big needs a thesis check |
| `--max-heat` | 6% of capital | The total loss if every stop is hit together |
| `--band` / `--min-trade` | 1 pp / ₹1,000 | Avoids churn where DP charges (~₹15 per scrip per sell day) and STT eat the benefit |

Holdings without a `sector` use a built-in map of about 55 NIFTY 50 names, marked `*`, which are also
treated as large caps. Anything else shows as **Unknown**, so add the column.

## Reading the results in an Indian context

- **Your pledge vs promoter pledge.** `pledged_qty` is shares you pledged for F&O margin. A fall shrinks
  collateral and can trigger forced square-offs. `promoter_pledge` above 20% is a governance red flag;
  see `fundamental-screening`.
- **ASM/GSM/ESM and BE/BZ series.** These bring higher margins, trade-for-trade settlement and tight
  price bands. Exits get slow just when you need them.
- **SME stocks** (NSE Emerge, BSE SME; series SM/ST) trade in large lots with thin books. Size them as
  illiquid, whatever their weight.
- **Group concentration.** Three Adani or Tata companies at 8% each fit under the single-stock limit
  but form one 24% bet on a single promoter group. Add a `group` column; a small built-in map covers
  common NIFTY names.
- **Correlated clusters** from `risk`, such as private banks, PSU banks or IT exporters, are where
  diversification is weaker than the stock count suggests.
- **Beta** above about 1.2 means a 10% NIFTY fall is likely to cost more than 10%. With cash, the
  "incl. cash" beta is the one that matters.

## Tax-aware rebalancing

`rebalance` sells oldest lots first (FIFO, as for demat shares) and takes the holding-period rules,
grandfathering and rates from `indian-tax-for-traders` (`tax.py`). Charges come from `trading-costs`
(`../trading-costs/scripts/charges.py`). For each sale it flags:
- **WAIT?** A profitable short-term lot turns long-term within `--wait-days` (default 60). Selling now is
  taxed at 20%; waiting brings it to 12.5%, or nil inside the ₹1.25 lakh exemption. Weigh the tax saved
  against the price risk.
- **LTCG inside the exemption.** Pass `--realized-ltcg` so the remaining exemption is right.
- **Booked losses.** Short-term losses offset STCG or LTCG; long-term losses offset only LTCG.

Prefer `--no-sell` (new SIP or bonus money into underweights) when selling would realise STCG.
For harvesting ideas, run `tax.py harvest` on the same file; `review` already lists them.

## How it fits with other skills

- `market-regime` sets how much equity exposure makes sense. `portfolio-review` checks what you hold.
  In a risk-off regime, look at heat and beta first.
- `sector-rotation` says which sectors lead. Feed its view into a `sector,weight` targets file.
- `position-sizing` and `stop-loss-strategies` supply the `stop` column that makes heat meaningful.
- `trading-discipline` runs the pre-trade gate. Treat heat above the limit, or a WARN on the stock or
  sector you are adding to, as a reason to stop at that gate.

## Output

```
Portfolio review as of 2026-11-01 (6 stocks, 7 lots)
  Holdings ₹8,00,000 | Cash ₹2,00,000 (20.0%) | Total ₹10,00,000 (₹10.00 L)
  Invested ₹7,10,000 | Unrealised P&L ₹90,000 (+12.68%) | Top-5 76.0%
  Sectors (limit 25%): Information Technology 55.0%, Energy 10.5%, ...
  Tax clock: 1 lot turns long-term within 30 days, 1 in 31–60 days
  REVIEW AAA is 30.0% of capital (single-stock limit 10%).
```

Lead with the two or three flags that matter most, then the numbers. Say which inputs were missing
(sector, buy dates, prices). Never turn a flag into an order. Orders follow the `broker-integration`
confirmation protocol.

_Educational analysis, not investment or tax advice. Data: [holdings file + as-of date]._

© Shubham Kumar · MIT · Shubhamkumartrichy/claude-trading-skills-india

Similar skills

All skills for Finance and business →

From the same set36

The whole set →
fno-options-analysis The fno-options-analysis Claude Code skill analyses Indian futures and options, including option chains, volatility, Greeks and expiries. It activates for questions about NIFTY, PCR, India VIX, margins or expiry rules. CX Codex +1 ★ 69repo stars breakout-planner breakout-planner — a Claude Code skill that evaluates breakout setups for NSE/BSE stocks and works out a trade plan. It responds to requests about Stage 2 trends, bases, entry points, or scanning a stock list. CX Codex +1 ★ 69repo stars stock-screener The stock-screener Claude Code skill filters and ranks Indian stocks using fundamentals from a CSV. It runs on requests to screen a company list, find stocks by financial criteria, or explain a failed rule. CX Codex +1 ★ 69repo stars results-season The results-season Claude Code skill analyzes how NSE and BSE stocks move after quarterly results. It scores price gaps, trading volume, and follow-through. CX Codex +1 ★ 69repo stars market-regime The market-regime Claude Code skill classifies market conditions from index or ETF data. It runs on questions about NIFTY’s trend and exposure before new trades. CX Codex +1 ★ 69repo stars momentum-scanner The momentum-scanner Claude Code skill scans NSE/BSE stocks for short-term momentum. It responds to requests about breakouts, news gaps and relative-strength rankings. CX Codex +1 ★ 69repo stars trading-discipline The trading-discipline Claude Code skill checks trade plans before an order and calculates allowed risk from a journal. It responds to questions about taking a trade, loss limits, or a losing streak. CX Codex +1 ★ 69repo stars event-calendar The event-calendar Claude Code skill tracks events that can affect Indian markets. It responds to questions about expiries, RBI meetings, economic releases, and event risk over a trade window. CX Codex +1 ★ 69repo stars

Project sponsors

Companies that keep this analytics open